ON A CHARACTERIZATION OF THE THREE LIMITING TYPES OF THE EXTREME.

Abstract

If X and Y are independent random variables then they are said to be completely confounding if the distributions of Z, Z conditional on Z = X, Z conditional on Z = Y are the same. If X, Y, and Z completely confound one another where Y and Z have the same distribution as aX + b and cX + d which are basically different linear functions, then the distribution of X is one of the three limiting types of the extreme (minimum) observation from independent samples from the same population. (Author)

Document Details

Document Type
Technical Report
Publication Date
Feb 01, 1965
Accession Number
AD0610845

Entities

People

  • J. Sethuraman

Organizations

  • Stanford University

Tags

DTIC Thesaurus Topics

  • Acquisition
  • Data Acquisition
  • Observation
  • Random Variables

Fields of Study

  • Mathematics

Readers

  • Graph Algorithms and Convex Optimization.
  • Regression Analysis.